Streamflow Forecasting at Ungaged Sites using Support Vector Machines

Zakaria, Zahrahtul and Shabri, Ani (2012) Streamflow Forecasting at Ungaged Sites using Support Vector Machines. Applied Mathematical Sciences, 6 (60). pp. 3003-3014. ISSN 1314-7552 (Printed) 1312-885X (Online)

[img] Text
Restricted to Registered users only

Download (520Kb) | Request a copy


Developing reliable estimates of streamflow prediction are crucial for water resources management and flood forecasting purposes. The objectives of this study are to investigate the potential of support vector machines (SVM) model for streamflow forecasting at ungaged sites, and to compare its performance with other statistical method of multiple linear regression (MLR). Three quantitative standard statistical indices such as mean absolute error (MAE), root mean square error (RMSE) and Nash-Sutcli�ffe coefficient of e�fficiency (CE) are employed to validate both models. The performances of both models are assessed by forecasting annual maximum flow series from 88 water level stations in Peninsular Malaysia. Based on these results, it was found that the SVM model outperforms the prediction ability of the traditional MLR model under all of the designated return periods.

Item Type: Article
Keywords: multiple linear regression, streamflow forecasting, support vector machines, ungaged site
Subjects: Q Science > Q Science (General)
Faculty / Institute: Faculty of Informatics & Computing
Depositing User: Dr Zahrahtul Amani Zakaria
Date Deposited: 13 Jan 2015 08:37
Last Modified: 13 Jan 2015 08:37

Actions (login required)

View Item View Item